Computational modelling and optimisation of a bone-scaffold fixation-plate biomechanical system
Project Description: Mr. Ferguson’s doctoral thesis involves the research and development of a novel, additively manufactured tissue scaffold-fixation system, which is used to reconstruct a jawbone with a large defect. The system is optimized through subject-specific numerical modelling methods and experimental tests.
Implantable Biosensors to Monitor and Stimulate Tissue Regeneration
Project Description: The recording and utilisation of muscle tissue electrical activity, otherwise known as myoelectric signals, has considerable importance in the bioelectronics field. A myoelectric sensor is a device that records and transmits myoelectric signals, by interfacing with muscle tissue. This is the premise for their usage as control inputs, such as in prostheses, functional electrical stimulation (FES), and wearable and remote robotic devices. Myoelectric sensors are also used in diagnostics, to assess or diagnose neuromuscular performance, injuries and syndromes. Furthermore, they are utilised for kinesiology studies, such as gait analysis.
Surface myoelectric sensors (SMES) and implantable myoelectric sensors (IMES) will be researched and developed, in affiliation with The University of Sydney and the ARC TCIBE. This will be achieved by utilising fastidious engineering approaches, such as 3D-printing and laser-cutting, to produce biocompatible and efficacious sensors. The myoelectric sensors will connect to external circuitry, for post-processing and analysis, to fulfill their intended bioelectronic application.
Deep learning based radiomics framework for the analysis of Soft-tissue Sarcomas in omni-modality images
Project Description: The implementation and availability of high-throughput computing has made it possible to extract innumerable features from medical imaging datasets. These extracted features can reveal disease related characteristics that can relate to prognosis, for example, predicting the development of distant metastases or overall survival rate of patients. The process of converting visual imaging data into mineable quantitative features is referred to radiomics. Radiomics is an emerging ﬁeld of translational research in medical imaging where the modalities include digital radiography, magnetic resonance imaging (MRI), computed tomography (CT), combined positron emission tomography – computed tomography (PET-CT) etc. We will propose a radiomics framework for the analysis of soft-tissue sarcomas in omni-modality images, using state-of-the-art convolutional neural networks – a data-driven approach to identify the quantifiable image characteristics that are most relevant for a particular task – in this case, patients’ outcome prediction. The key challenge will be to train the CNNs across all image types (both functional and anatomical) to identify the correlations between them so that prognosis related information can be learned regardless of the image type. Ultimately, our proposed framework could potentially improve both diagnostic and prognostic processes by allowing automated omni-modality information fusion for the analysis of soft-tissue sarcomas.